nchain is a flexible and efficent framework to create LLM bots using embeddings over extensible dataset
Project description
nChain
nChain is a Python package that provides a flexible and efficient implementation to create LLM bots over extensible dataset.
Installation
You can install nChain directly from PyPI using pip:
pip install nChain
Alternatively, you can clone the repository and install from source:
git clone https://github.com/jamesliu/nChain.git
cd nChain
pip install .
Usage
Here are examples of how to use nChain to search ArXiv paper using embedding.
nchain add https://arxiv.org/abs/1409.0473
nchain add https://arxiv.org/abs/2010.14701
nchain add https://arxiv.org/abs/2203.02155
nchain add https://arxiv.org/abs/2302.01318v1
nchain add https://arxiv.org/abs/2309.17453
nchain add https://arxiv.org/abs/2310.02304
nchain query "Show me the Scaling Laws for Autoregressive Generative Modeling."
nchain query "Show me the algorithm about Large Lanuage Model Decoding with Speculative Sampling."
nchain query "How to handle streaming apps efficiently in LLM?"
Documentation
Full documentation is available here.
Contributing
We welcome contributions to nChain! If you're interested in contributing, please see our contribution guidelines and code of conduct.
License
nChain is licensed under the Apache License 2.0. See the LICENSE file for more details.
Support
For support, questions, or feature requests, please open an issue on our GitHub repository or contact the maintainers.
Changelog
See the releases page for a detailed changelog of each version.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for nchain-0.13.post4-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | e59c4b7a3a74c7ddb2a956ca6f4835774dd2acc78028c143eed3b65761244947 |
|
MD5 | 9b92a58544c85ea92531cf483165dcca |
|
BLAKE2b-256 | 31c530005b27796070b58597d7ff25980c61085ed3c8ec5dbefc3ada20f0b053 |